SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.09277 · NeurIPS · 2021

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

Sejun Park, Jinwoo Shin, Jongheon Jeong, Minkyu Kim, Heung-Chang Lee, Doguk Kim

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2111.09277.json · badge: /api/ran/2111.09277.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jh-jeong/smoothmix canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
SmoothAdv_PGD Ran
ran on a synthesized input · constructed an object; no result was computed
jh-jeong/smoothmix/code/train_consistency.py
code served (permissive licence) · get_code("4d445e966929e029")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SmoothAdv_PGD: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal model that accepts inputs and returns logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        # Flatten and pass through linear layer
        batch_size = x.size(0)
        x_flat = x.view(batch_size, -1)
        return self.fc(x_flat)

# Create model instance
model = SimpleModel(input_dim=4, num_classes=3)
model.eval()

# Create tiny batch of inputs in [0, 1] range
# batch_size=2, spatial dims=1x4 to get total 4 features
inputs = torch.rand(2, 1, 4)

# Create labels (class indices for 3 classes)
labels = torch.tensor([0, 1])

# Create noise samples (list of noise tensors with same shape as inputs)
noises = [torch.randn(2, 1, 4) * 0.01 for _ in range(2)]

# Device
device = torch.device('cpu')

# Build ARGS dict with all parameters
ARGS = {
    'steps': 3,
    'random_start': True,
    'max_norm': 0.3,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SmoothAdv_PGD — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SmoothAdv_PGD output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Attacker Not yet run
unverified (harvested, no recorded run)
jh-jeong/smoothmix/code/train_consistency.py
code served (permissive licence) · get_code("dff4428e257e2940")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against 2 -adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the prediction confidence, i.e., the higher confidence from a smoothed classifier implies the better robustness. This motivates us to rethink the fundamental trade-off between accuracy and robustness in terms of calibrating confidences of a smoothed classifier. In this paper, we propose a simple training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup: it trains on convex combinations of samples along the direction of adversarial perturbation for each input. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness in case of smoothed classifiers, and offers an intuitive way to adaptively set a new decision boundary between these samples for better robustness. Our experimental results demonstrate that the proposed method can significantly improve the certified 2 -robustness of smoothed classifiers compared to existing state-of-the-art robust training methods. 3 * Work done at KAIST. † Work done at Kakao Enterprise. 3 Code is available at https://github.com/jh-jeong/smoothmix.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2111.09277")
get_code_for_paper("2111.09277")
have("2111.09277")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2111.09277.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2111.09277.svg)](https://syntology.ai/paper/2111.09277)

Connect an agent — have() is free.